Skip to contentSkip to conversation

nohz: Move nohz kick out of scheduler IPI

GIT PULL New Frederic Weisbecker 2 participants 8 messages Apr 3, 2014 – Apr 16, 2014

Subsystems (2)
lore
Share & tools
lore
#0 lore raw

Ingo, Thomas,

Please pull the timers/nohz-ipi-for-tip-v3 branch that can be found at:

git://git.kernel.org/pub/scm/linux/kernel/git/frederic/linux-dynticks.git
timers/nohz-ipi-for-tip-v3

It is based on 7a48837732f87a574ee3e1855927dc250117f565 ("Merge branch 'for-3.15/core' of git://git.kernel.dk/linux-block")
due to dependencies on the block tree containing IPI core changes.

This v2 addresses Paul review and add his reviewed-by tags.

I'm trying to get these 2 patches in before the merge window ends otherwise we'll have to do tricky branch split on the next cycle.

---
When a full dynticks CPU runs in single task mode then a new task gets enqueued, we notify it through an IPI such that it restarts its tick.

The IPI used here is the scheduler IPI. There are a few reasons for that:
it can be called when interrupts are disabled, it can be called concurrently... These convenient properties altogether aren't yet offered by the IPI subsystem.

Meanwhile, bloating that way the scheduler IPI with scheduler unrelated code is an abuse of this fast path. We certainly don't want to start a big kernel IPI.

So this patchset adds a small helper to the IPI subsystem that allows to queue an IPI from interrupt disabled code while handling concurrent callers as well. Eventually the nohz kick gets converted to this new facility.

Partly inspired by a suggestion from Peter Zijlstra.

* Patch 1/2 brings the IPI infrastructure to support this
* Patch 2/2 does the nohz IPI conversion

Thanks,
Frederic
---

Frederic Weisbecker (2):
smp: Non busy-waiting IPI queue
nohz: Move full nohz kick to its own IPI

 include/linux/smp.h      | 11 +++++++++++
 include/linux/tick.h     |  2 ++
 kernel/sched/core.c      |  5 +----
 kernel/sched/sched.h     |  2 +-
 kernel/smp.c             | 42 ++++++++++++++++++++++++++++++++++++++++++
 kernel/time/tick-sched.c | 21 +++++++++++++++++++++
 6 files changed, 78 insertions(+), 5 deletions(-)
#1 lore raw

PATCH 1/2 smp: Non busy-waiting IPI queue

Some IPI users, such as the nohz subsystem, need to be able to send an async IPI (async = non waiting for any other IPI completion) on contexts with disabled interrupts. And we want the IPI subsystem to handle concurrent calls by itself.

Currently the nohz machinery uses the scheduler IPI for this purpose because it can be triggered from any context and doesn't need any serialization from the caller. But this is an abuse of a scheduler fast path. We are bloating it with a job that should use its own IPI.

The current set of IPI functions can't be called when interrupts are disabled otherwise we risk a deadlock when two CPUs wait for each other's IPI completion.

OTOH smp_call_function_single_async() can be called when interrupts are disabled. But then it's up to the caller to serialize the given IPI. This can't be called concurrently without special care.

So we need a version of the async IPI that takes care of concurrent calls.

The proposed solution is to synchronize the IPI with a specific flag that prevents the IPI from being sent if it is already pending but not yet executed. Ordering is maintained such that, if the IPI is not sent because it's already pending, we guarantee it will see the new state of the data we expect it to when it will execute.

This model is close to the irq_work design. It's also partly inspired by suggestions from Peter Zijlstra.

Cc Andrew Morton <[email protected]>
Cc Ingo Molnar <[email protected]>
Cc Jens Axboe <[email protected]>
Cc Kevin Hilman <[email protected]>
Cc Paul E. McKenney <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Thomas Gleixner <[email protected]>
---
 include/linux/smp.h | 11 +++++++++++
 kernel/smp.c        | 42 ++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 53 insertions(+)
include/linux/smp.h +11 -0
index 633f5ed..0de1eff 100644
@@ -29,6 +29,17 @@ extern unsigned int total_cpus;
 int smp_call_function_single(int cpuid, smp_call_func_t func, void *info,
 			     int wait);
 
+struct queue_single_data;
+typedef void (*smp_queue_func_t)(struct queue_single_data *qsd);
+
+struct queue_single_data {
+	struct call_single_data data;
+	smp_queue_func_t func;
+	int pending;
+};
+
+int smp_queue_function_single(int cpu, struct queue_single_data *qsd);
+
 /*
  * Call a function on all processors
  */
kernel/smp.c +42 -0

48 lines not on this page · raw message

Signature · 1 line
1.8.3.1
#2 lore raw

PATCH 2/2 nohz: Move full nohz kick to its own IPI

In reply to Frederic Weisbecker

Now that we have smp_queue_function_single() which can be used to safely queue IPIs when interrupts are disabled and without worrying about concurrent callers, lets use it for the full dynticks kick to notify a CPU that it's exiting single task mode.

This unbloats a bit the scheduler IPI that the nohz code was abusing for its cool "callable anywhere/anytime" properties.

Cc Andrew Morton <[email protected]>
Cc Ingo Molnar <[email protected]>
Cc Jens Axboe <[email protected]>
Cc Kevin Hilman <[email protected]>
Cc Paul E. McKenney <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Thomas Gleixner <[email protected]>
---
 include/linux/tick.h     |  2 ++
 kernel/sched/core.c      |  5 +----
 kernel/sched/sched.h     |  2 +-
 kernel/time/tick-sched.c | 21 +++++++++++++++++++++
 4 files changed, 25 insertions(+), 5 deletions(-)
include/linux/tick.h +2 -0
index b84773c..9d3fcc2 100644
@@ -182,6 +182,7 @@ static inline bool tick_nohz_full_cpu(int cpu)
 extern void tick_nohz_init(void);
 extern void __tick_nohz_full_check(void);
 extern void tick_nohz_full_kick(void);
+extern void tick_nohz_full_kick_cpu(int cpu);
 extern void tick_nohz_full_kick_all(void);
 extern void __tick_nohz_task_switch(struct task_struct *tsk);
 #else
@@ -190,6 +191,7 @@ static inline bool tick_nohz_full_enabled(void) { return false; }
 static inline bool tick_nohz_full_cpu(int cpu) { return false; }
 static inline void __tick_nohz_full_check(void) { }
 static inline void tick_nohz_full_kick(void) { }
+static inline void tick_nohz_full_kick_cpu(int cpu) { }
 static inline void tick_nohz_full_kick_all(void) { }
 static inline void __tick_nohz_task_switch(struct task_struct *tsk) { }
 #endif
kernel/sched/core.c +1 -4
index 9cae286..e4b344e 100644
@@ -1499,9 +1499,7 @@ void scheduler_ipi(void)
 	 */
 	preempt_fold_need_resched();
 
-	if (llist_empty(&this_rq()->wake_list)
-			&& !tick_nohz_full_cpu(smp_processor_id())
-			&& !got_nohz_idle_kick())
+	if (llist_empty(&this_rq()->wake_list) && !got_nohz_idle_kick())
 		return;
 
 	/*
@@ -1518,7 +1516,6 @@ void scheduler_ipi(void)
 	 * somewhat pessimize the simple resched case.
 	 */
 	irq_enter();
-	tick_nohz_full_check();
 	sched_ttwu_pending();
 
 	/*
kernel/sched/sched.h +1 -1
index c9007f2..4771063 100644
@@ -1225,7 +1225,7 @@ static inline void inc_nr_running(struct rq *rq)
 		if (tick_nohz_full_cpu(rq->cpu)) {
 			/* Order rq->nr_running write against the IPI */
 			smp_wmb();
-			smp_send_reschedule(rq->cpu);
+			tick_nohz_full_kick_cpu(rq->cpu);
 		}
        }
 #endif
kernel/time/tick-sched.c +21 -0
index 9f8af69..582d3f6 100644
@@ -230,6 +230,27 @@ void tick_nohz_full_kick(void)
 		irq_work_queue(&__get_cpu_var(nohz_full_kick_work));
 }
 
+static void nohz_full_kick_queue(struct queue_single_data *qsd)
+{
+	__tick_nohz_full_check();
+}
+
+static DEFINE_PER_CPU(struct queue_single_data, nohz_full_kick_qsd) = {
+	.func = nohz_full_kick_queue,
+};
+
+void tick_nohz_full_kick_cpu(int cpu)
+{
+	if (!tick_nohz_full_cpu(cpu))
+		return;
+
+	if (cpu == smp_processor_id()) {
+		irq_work_queue(&__get_cpu_var(nohz_full_kick_work));
+	} else {
+		smp_queue_function_single(cpu, &per_cpu(nohz_full_kick_qsd, cpu));
+	}
+}
+
 static void nohz_full_kick_ipi(void *info)
 {
 	__tick_nohz_full_check();
Signature · 1 line
1.8.3.1
#3 lore raw
In reply to Frederic Weisbecker
Quoted 6 lines · Frederic Weisbecker

Ingo, Thomas,

Please pull the timers/nohz-ipi-for-tip-v3 branch that can be found at:

git://git.kernel.org/pub/scm/linux/kernel/git/frederic/linux-dynticks.git
timers/nohz-ipi-for-tip-v3

Ping?

maintainer
#4 lore raw
Quoted 9 lines · Frederic Weisbecker
Quoted 6 lines · Frederic Weisbecker

Ingo, Thomas,

Please pull the timers/nohz-ipi-for-tip-v3 branch that can be found at:

git://git.kernel.org/pub/scm/linux/kernel/git/frederic/linux-dynticks.git
timers/nohz-ipi-for-tip-v3

Ping?

So this came a bit late - will it be fine for v3.16 as-is?

Thanks,

Ingo

#5 lore raw
Quoted 6 lines · Ingo Molnar
Quoted 3 lines · Frederic Weisbecker
Quoted 2 lines · Frederic Weisbecker

Ingo, Thomas,

Quoted 8 lines
Quoted 6 lines
Quoted 4 lines

Please pull the timers/nohz-ipi-for-tip-v3 branch that can be found at:

git://git.kernel.org/pub/scm/linux/kernel/git/frederic/linux-dynticks.git
timers/nohz-ipi-for-tip-v3

Ping?

So this came a bit late - will it be fine for v3.16 as-is?

It was late on purpose due to dependencies on the block tree. But nevermind.

It's still fine to be pulled as is after -rc1 for 3.16.

Thanks!

Quoted 3 lines

Thanks,

Ingo

maintainer
#6 lore raw
Quoted 9 lines · Frederic Weisbecker
Quoted 8 lines · Ingo Molnar
Quoted 5 lines · Frederic Weisbecker
Quoted 4 lines · Frederic Weisbecker

Ingo, Thomas,

Please pull the timers/nohz-ipi-for-tip-v3 branch that can be found at:

Quoted 8 lines
Quoted 6 lines
Quoted 4 lines
Quoted 2 lines

git://git.kernel.org/pub/scm/linux/kernel/git/frederic/linux-dynticks.git
timers/nohz-ipi-for-tip-v3

Ping?

So this came a bit late - will it be fine for v3.16 as-is?

It was late on purpose due to dependencies on the block tree. [...]

Well, changing the generic SMP IPI facilities via the block tree was indeed a problem.

Quoted 3 lines

But nevermind.

It's still fine to be pulled as is after -rc1 for 3.16.

Ok, will do.

Thanks,

Ingo

maintainer
#7 lore raw
In reply to Frederic Weisbecker
Quoted 48 lines · Frederic Weisbecker

Ingo, Thomas,

Please pull the timers/nohz-ipi-for-tip-v3 branch that can be found at:

git://git.kernel.org/pub/scm/linux/kernel/git/frederic/linux-dynticks.git
timers/nohz-ipi-for-tip-v3

It is based on 7a48837732f87a574ee3e1855927dc250117f565 ("Merge branch 'for-3.15/core' of git://git.kernel.dk/linux-block")
due to dependencies on the block tree containing IPI core changes.

This v2 addresses Paul review and add his reviewed-by tags.

I'm trying to get these 2 patches in before the merge window ends otherwise we'll have to do tricky branch split on the next cycle.

---
When a full dynticks CPU runs in single task mode then a new task gets enqueued, we notify it through an IPI such that it restarts its tick.

The IPI used here is the scheduler IPI. There are a few reasons for that:
it can be called when interrupts are disabled, it can be called concurrently... These convenient properties altogether aren't yet offered by the IPI subsystem.

Meanwhile, bloating that way the scheduler IPI with scheduler unrelated code is an abuse of this fast path. We certainly don't want to start a big kernel IPI.

So this patchset adds a small helper to the IPI subsystem that allows to queue an IPI from interrupt disabled code while handling concurrent callers as well. Eventually the nohz kick gets converted to this new facility.

Partly inspired by a suggestion from Peter Zijlstra.

* Patch 1/2 brings the IPI infrastructure to support this
* Patch 2/2 does the nohz IPI conversion

Thanks,
Frederic
---

Frederic Weisbecker (2):
smp: Non busy-waiting IPI queue
nohz: Move full nohz kick to its own IPI

Quoted 7 lines
 include/linux/smp.h      | 11 +++++++++++
 include/linux/tick.h     |  2 ++
 kernel/sched/core.c      |  5 +----
 kernel/sched/sched.h     |  2 +-
 kernel/smp.c             | 42 ++++++++++++++++++++++++++++++++++++++++++
 kernel/time/tick-sched.c | 21 +++++++++++++++++++++
 6 files changed, 78 insertions(+), 5 deletions(-)

Pulled into tip:timers/nohz, thanks a lot Frederic!

Ingo